Jingfeng Wu

发表

STOCHASTIC GRADIENT DESCENT WITH MODERATE LEARNING RATE

Difan Zou, Jingfeng Wu, 2021 .

Obtaining Regularization for Free via Iterate Averaging

Lin F. Yang, V. Braverman, Jingfeng Wu, 2019 .

Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression

S. Kakade, Quanquan Gu, V. Braverman, 2021, ICML.

Twenty Years After: Hierarchical Core-Stateless Fair Queueing

Vladimir Braverman, Ion Stoica, Zhuolong Yu, 2021, NSDI.

Ship Compute or Ship Data? Why Not Both?

Mosharaf Chowdhury, Jie You, Jingfeng Wu, 2021, NSDI.

Programmable packet scheduling with a single queue

Vladimir Braverman, Mosharaf Chowdhury, Zhuolong Yu, 2021, SIGCOMM.

The Regularization Effects of Anisotropic Noise in Stochastic Gradient Descent pdf

Lei Wu, Zhanxing Zhu, Jinwen Ma, 2018, ArXiv.

Lifelong Learning with Sketched Structural Regularization pdf

Vladimir Braverman, Soheil Kolouri, Praveen K. Pilly, 2021, ACML.

Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate

Vladimir Braverman, Quanquan Gu, Difan Zou, 2020, ICLR.

The Multiplicative Noise in Stochastic Gradient Descent: Data-Dependent Regularization, Continuous and Discrete Approximation pdf

Zhanxing Zhu, Haoyi Xiong, Wenqing Hu, 2019, ArXiv.

Direction Matters: On the Implicit Regularization Effect of Stochastic Gradient Descent with Moderate Learning Rate pdf

Vladimir Braverman, Quanquan Gu, Jingfeng Wu, 2020, ICLR.

Proceedings of the 18th USENIX Symposium on Networked Systems Design and Implementation

Jingfeng Wu, Zhuolong Yu, Systems Design, 2021 .